Instructions to use SargeDev/Solar-Decision-JEV-27B-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SargeDev/Solar-Decision-JEV-27B-V2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SargeDev/Solar-Decision-JEV-27B-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SargeDev/Solar-Decision-JEV-27B-V2")
model = AutoModelForCausalLM.from_pretrained("SargeDev/Solar-Decision-JEV-27B-V2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SargeDev/Solar-Decision-JEV-27B-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SargeDev/Solar-Decision-JEV-27B-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SargeDev/Solar-Decision-JEV-27B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SargeDev/Solar-Decision-JEV-27B-V2

SGLang

How to use SargeDev/Solar-Decision-JEV-27B-V2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SargeDev/Solar-Decision-JEV-27B-V2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SargeDev/Solar-Decision-JEV-27B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SargeDev/Solar-Decision-JEV-27B-V2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SargeDev/Solar-Decision-JEV-27B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SargeDev/Solar-Decision-JEV-27B-V2 with Docker Model Runner:
```
docker model run hf.co/SargeDev/Solar-Decision-JEV-27B-V2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Solar-Decision-JEV-27B-V2

The r32 + solar(V2) merge. huihui Qwen3.8-27B-abliterated + the AutoTrust r32 lm_head LoRA + our solar r16 LoRA re-trained to step 1894 (second full pass over the corpus), merged by direct LoRA-delta arithmetic.

This is the V2 of SargeDev/Solar-Decision-JEV-27B. Same architecture and merge recipe; the only change is the solar half, trained far past the V1 checkpoint (step 1219 → step 1894, ~55% further through the cosine schedule with a full second epoch of data).

The decision readout is trained INTO the model, so a typed decision is a single prefill with max_tokens=1, constrained to the option tokens, read back as log-probabilities. No separate head to run. (vLLM only — llama.cpp does not return the per-token logprobs this path needs.)

Gate results, honestly (27,695 rows, same harness/head/calibration as every number below)

model	choice top-1	score top-1	noul AUROC	overall top-1
AutoTrust (published reference)	0.9041	0.8910	0.9961	—
r32 + lm_head alone	0.8693	0.8135	0.9919	0.886
this repo (r32 + solar-1894)	0.8278	0.7424	0.9831	0.839
V1 (r32 + solar-1219)	0.8162	0.7192	0.9810	0.817
solar r16 alone (1219, separate head)	0.5054	0.5369	0.9449	—

What training solar harder bought us: the combined merge improved on V1 on every cell (choice +1.2 pts, score +2.3 pts, AUROC +0.002, overall +2.2 pts). The direction is real. But it is still below r32-alone on the decision cells, for the same structural reason: r32 trains the decision distribution into lm_head; solar has no lm_head LoRA, so stacking its delta dilutes a readout r32 had already specialized. More solar training shrinks the penalty; it does not erase it.

One calibration caveat, stated plainly: choice ECE here is 0.145 (r32-alone is ~0.03 on this kind). V2's typed-decision top picks are decent; its typed confidences on choice are less trustworthy than r32's. noul ECE is fine (0.007).

If you want the best decision instrument we ship, use SargeDev/Solar-JEV-27B-R32 (r32 alone) or SargeDev/JEV-27B-Uncensored. Use this V2 if you want the merge of both lines (e.g. for the everyday-chat behavior the solar line carries) and accept the measured cost above.

Everyday chat

Same as the rest of the Solar family: plain-English conversation is the solar line's home turf — crisp calls with honestly stated confidence, no hedge-fest. Pass enable_thinking: false in chat_template_kwargs (or --default-chat-template-kwargs at serve time) or the template emits its reasoning trace into the answer.

Serving

vllm serve SargeDev/Solar-Decision-JEV-27B-V2 \
  --served-model-name solar-jev-27b-v2 \
  --trust-remote-code --max-model-len 8192 \
  --default-chat-template-kwargs '{"enable_thinking": false}'

Quantizations of this model

SargeDev/Solar-Decision-JEV-27B-V2-GGUF — 11-quant ladder (IQ4_XS…Q8_0), nextn/MTP drafter tensors preserved for speculative decoding. Fast everyday chat; not a typed-decision instrument (llama.cpp exposes no token logprobs).
SargeDev/Solar-Decision-JEV-27B-V2-NVFP4-FP8 — NVFP4 W4A4 (attn + gate/up) + FP8 down_proj via llm-compressor, serves in vLLM with --quantization compressed-tensors.

Lineage & credits

AutoTrust AI — the r16/r32 decision LoRA recipe, the 24-slot decision head, and the serve/decision machinery (autotrust/JEV-27B).
huihui-ai — the abliterated (uncensored) Qwen3.8-27B backbone (Huihui-Qwen3.8-27B-abliterated).
SargeDev — the distillation corpora: the question/state corpus (jev-distill-corpus-v3 and the per-domain jev-corpus-* split), and — for our solar LoRA — the typed-decision labels (solar-decisions-corpus-v4, 816,741 calibrated-distribution targets labeled by upstage/solar-decide-flash: a full relabel of v3 plus 120k new rows). The r32 half trains on the v3-lineage targets; the solar half trains on the v4 targets.
Qwen — the base architecture.

Built on 2× NVIDIA GB10 (DGX Spark). Apache-2.0.

Downloads last month: 440

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for SargeDev/Solar-Decision-JEV-27B-V2

Base model

Qwen/Qwen3.8-27B

Finetuned

huihui-ai/Huihui-Qwen3.8-27B-abliterated

Finetuned

(12)

this model

Quantizations

3 models

SargeDev
/

Solar-Decision-JEV-27B-V2